Upload folder using huggingface_hub

README.md

@@ -0,0 +1,140 @@
+---
+license: mit
+pipeline_tag: tabular-regression
+tags:
+- chemistry
+- microbiology
+- antibiotics
+library_name: duvida
+datasets:
+- scbirlab/thomas-2018-spark-wt
+---
+
+# Predictor of _Francisella tularensis_ MICs 
+
+_Updated:_ Fri 28 Mar 18:11:30 GMT 2025
+
+Trained on the _Francisella tularensis_, WT accumulator phenotype subset of the [human-curated SPARK dataset](https://doi.org/10.1021/acsinfecdis.8b00193) ( rows in total for _Francisella tularensis_).
+
+## Model details
+
+This model was trained using [our Duvida framework](https://github.com/scbirlab/duvida), 
+as a result of hyperparameter searches and selecting the model that performs best on unseen test data 
+(from a scaffold split). 
+
+Duvida also saves the training data in this checkpoint to allows the calculation of uncertainty metrics 
+based on that training data.
+
+This model is the best regression model from a hyperparameter search, determined
+by Spearman's $\rho$ on a held-out test set not used in training or early stopping. 
+
+### Model architecture
+
+- **Regression**
+
+```json
+
+{
+    "dropout": 0.2,
+    "ensemble_size": 10,
+    "extra_featurizers": null,
+    "learning_rate": 0.0001,
+    "model_class": "FPMLPModelBox",
+    "n_hidden": 5,
+    "n_units": 16,
+    "use_2d": true,
+    "use_fp": true
+}
+```
+
+### Model usage
+
+You can use this model with:
+
+```python
+from duvida.autoclasses import AutoModelBox
+modelbox = AutoModelBox.from_pretrained("hf://scbirlab/spark-dv-2503-ftul")
+modelbox.predict(filename=..., inputs=[...], columns=[...])  # make predictions on your own data
+```
+
+## Training details
+
+- **Dataset:** [SPARK, WT accumulator, _Francisella tularensis_ subset](https://huggingface.co/datasets/scbirlab/thomas-2018-spark-wt)
+- **Input column:** smiles
+- **Output column:** pmic
+- **Split type:** Murcko scaffold
+- **Split proportions:** 
+    - 70% training (6770 rows)
+    - 15% validation (for early stopping) (1450 rows)
+    - 15% test (for selecting hyperparameters) (1451 rows)
+
+Here is the training log:
+
+<img src="training-log.png" width=450>
+
+And these are the evaluation scores.
+
+Train (6770 rows):
+
+```json
+
+{
+    "Pearson r": 0.5315396541042405,
+    "RMSE": 0.1128498837351799,
+    "Spearman rho": 0.6696014953216823
+}
+```
+
+Validation (1450 rows):
+
+```json
+
+{
+    "Pearson r": 0.2988704143091524,
+    "RMSE": 0.12225893139839172,
+    "Spearman rho": 0.5774266044687701
+}
+```
+
+
+Test (1451 rows):
+
+```json
+
+{
+    "Pearson r": 0.3527353695023497,
+    "RMSE": 0.10296344012022018,
+    "Spearman rho": 0.618750940647444
+}
+```
+
+## Training data details
+
+The training data were collated by the authors of:
+
+> Joe Thomas, Marc Navre, Aileen Rubio, and Allan Coukell
+> Shared Platform for Antibiotic Research and Knowledge: A Collaborative Tool to SPARK Antibiotic Discovery
+> ACS Infectious Diseases 2018 4 (11), 1536-1539
+> DOI: 10.1021/acsinfecdis.8b00193
+
+We cleaned the original SPARK dataset to subset the most relevant columns, remove empty values, 
+give succint column titles, and split by species.
+
+This particular dataset retains only measurements on bacteria with wild-type accumulation phenotypes.
+
+### Dataset Sources
+
+- **Repository:** https://www.collaborativedrug.com/spark-data-downloads
+- **Paper:** https://doi.org/10.1021/acsinfecdis.8b00193
+
+### Data Collection and Processing
+
+Data were processed using [schemist](https://github.com/scbirlab/schemist), a tool for processing chemical datasets.
+
+The SMILES strings have been canonicalized, and split into training (70%), validation (15%), and test (15%) sets 
+by Murcko scaffold for each species with more than 1000 entries. Additional features like molecular weight and 
+topological polar surface area have also been calculated.
+
+### Who are the source data producers?
+
+Joe Thomas, Marc Navre, Aileen Rubio, and Allan Coukell

data-config.json

@@ -0,0 +1,17 @@
+{
+    "_default_cache": "cache/duvida/data",
+    "_in_key": "inputs",
+    "_input_cols": [
+        "smiles"
+    ],
+    "_label_cols": [
+        "pmic"
+    ],
+    "_out_key": "labels",
+    "input_shape": [
+        2248
+    ],
+    "output_shape": [
+        1
+    ]
+}

data-load-args.json

@@ -0,0 +1,10 @@
+{
+    "cache": "/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/models/spark/Francisella-tularensis/31/cache",
+    "features": [
+        "smiles"
+    ],
+    "filename": "/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-train.csv.gz",
+    "labels": [
+        "pmic"
+    ]
+}

eval-metrics_test.json

@@ -0,0 +1,5 @@
+{
+    "Pearson r": 0.3527353695023497,
+    "RMSE": 0.10296344012022018,
+    "Spearman rho": 0.618750940647444
+}

eval-metrics_train.json

@@ -0,0 +1,5 @@
+{
+    "Pearson r": 0.5315396541042405,
+    "RMSE": 0.1128498837351799,
+    "Spearman rho": 0.6696014953216823
+}

eval-metrics_validation.json

@@ -0,0 +1,5 @@
+{
+    "Pearson r": 0.2988704143091524,
+    "RMSE": 0.12225893139839172,
+    "Spearman rho": 0.5774266044687701
+}

input-data.hf/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf123b1b5ea8f059779d5f1785c9db1193db46a4750e6bf7f2e332a4c619b67
+size 690568

input-data.hf/dataset_info.json

@@ -0,0 +1,52 @@
+{
+  "builder_name": "csv",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "csv",
+  "dataset_size": 2688094,
+  "description": "",
+  "download_checksums": {
+    "/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-train.csv.gz": {
+      "num_bytes": 536218,
+      "checksum": null
+    }
+  },
+  "download_size": 536218,
+  "features": {
+    "smiles": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "inputs": {
+      "feature": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "labels": {
+      "feature": {
+        "dtype": "float64",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 3224312,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 2688094,
+      "num_examples": 6770,
+      "dataset_name": "csv"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

input-data.hf/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "98c4ff865d26cf29",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": "train"
+}

logs-csv/lightning_logs/version_0/hparams.yaml

@@ -0,0 +1,13 @@
+dropout: 0.2
+ensemble_size: 10
+extra_featurizers: null
+learning_rate: 0.0001
+n_hidden: 5
+n_input: 2248
+n_out: 1
+n_units: 16
+optimizer: !!python/name:torch.optim.adam.Adam ''
+reduce_lr_on_plateau: true
+reduce_lr_patience: 10
+use_2d: true
+use_fp: true

logs-csv/lightning_logs/version_0/metrics.csv

@@ -0,0 +1,155 @@
+epoch,learning_rate,loss,step,val_loss
+0,9.999999747378752e-05,,423,1.035925030708313
+0,,9.994428634643555,423,
+1,9.999999747378752e-05,,847,0.6954950094223022
+1,,3.126251697540283,847,
+2,9.999999747378752e-05,,1271,0.6660816073417664
+2,,2.558513641357422,1271,
+3,9.999999747378752e-05,,1695,0.5705931186676025
+3,,2.1037137508392334,1695,
+4,9.999999747378752e-05,,2119,0.49348127841949463
+4,,1.747497320175171,2119,
+5,9.999999747378752e-05,,2543,0.3814232051372528
+5,,1.4690725803375244,2543,
+6,9.999999747378752e-05,,2967,0.34099045395851135
+6,,1.2258453369140625,2967,
+7,9.999999747378752e-05,,3391,0.29116082191467285
+7,,1.0339215993881226,3391,
+8,9.999999747378752e-05,,3815,0.2379973977804184
+8,,0.9013144969940186,3815,
+9,9.999999747378752e-05,,4239,0.19984234869480133
+9,,0.7816758155822754,4239,
+10,9.999999747378752e-05,,4663,0.1637083888053894
+10,,0.6932660937309265,4663,
+11,9.999999747378752e-05,,5087,0.1320888251066208
+11,,0.6253244876861572,5087,
+12,9.999999747378752e-05,,5511,0.11645940691232681
+12,,0.5718656778335571,5511,
+13,9.999999747378752e-05,,5935,0.10740785300731659
+13,,0.5331162214279175,5935,
+14,9.999999747378752e-05,,6359,0.09628769755363464
+14,,0.5030606389045715,6359,
+15,9.999999747378752e-05,,6783,0.09018626809120178
+15,,0.47158119082450867,6783,
+16,9.999999747378752e-05,,7207,0.08879426121711731
+16,,0.4476066827774048,7207,
+17,9.999999747378752e-05,,7631,0.0879310742020607
+17,,0.4256654381752014,7631,
+18,9.999999747378752e-05,,8055,0.08867588639259338
+18,,0.4078732132911682,8055,
+19,9.999999747378752e-05,,8479,0.08685865998268127
+19,,0.3951185345649719,8479,
+20,9.999999747378752e-05,,8903,0.08222781866788864
+20,,0.3779689073562622,8903,
+21,9.999999747378752e-05,,9327,0.08167942613363266
+21,,0.3682374358177185,9327,
+22,9.999999747378752e-05,,9751,0.08089277893304825
+22,,0.3554483950138092,9751,
+23,9.999999747378752e-05,,10175,0.08071091026067734
+23,,0.3422313630580902,10175,
+24,9.999999747378752e-05,,10599,0.07949075102806091
+24,,0.3378938138484955,10599,
+25,9.999999747378752e-05,,11023,0.08147379755973816
+25,,0.32231298089027405,11023,
+26,9.999999747378752e-05,,11447,0.07940167188644409
+26,,0.3146795630455017,11447,
+27,9.999999747378752e-05,,11871,0.07670588791370392
+27,,0.3067043125629425,11871,
+28,9.999999747378752e-05,,12295,0.07626417279243469
+28,,0.30274152755737305,12295,
+29,9.999999747378752e-05,,12719,0.0779544860124588
+29,,0.2946133017539978,12719,
+30,9.999999747378752e-05,,13143,0.07719951868057251
+30,,0.29268163442611694,13143,
+31,9.999999747378752e-05,,13567,0.07851152867078781
+31,,0.28270256519317627,13567,
+32,9.999999747378752e-05,,13991,0.07809314876794815
+32,,0.2779752314090729,13991,
+33,9.999999747378752e-05,,14415,0.07809542864561081
+33,,0.27120184898376465,14415,
+34,9.999999747378752e-05,,14839,0.07520253211259842
+34,,0.2669171392917633,14839,
+35,9.999999747378752e-05,,15263,0.07598806172609329
+35,,0.26092231273651123,15263,
+36,9.999999747378752e-05,,15687,0.0762818232178688
+36,,0.2556494176387787,15687,
+37,9.999999747378752e-05,,16111,0.07429581135511398
+37,,0.252155065536499,16111,
+38,9.999999747378752e-05,,16535,0.07375046610832214
+38,,0.24888691306114197,16535,
+39,9.999999747378752e-05,,16959,0.07450631260871887
+39,,0.24435901641845703,16959,
+40,9.999999747378752e-05,,17383,0.0731251984834671
+40,,0.2419043779373169,17383,
+41,9.999999747378752e-05,,17807,0.07379607111215591
+41,,0.23947010934352875,17807,
+42,9.999999747378752e-05,,18231,0.0751994252204895
+42,,0.23747314512729645,18231,
+43,9.999999747378752e-05,,18655,0.07375573366880417
+43,,0.23268665373325348,18655,
+44,9.999999747378752e-05,,19079,0.07372378557920456
+44,,0.23062841594219208,19079,
+45,9.999999747378752e-05,,19503,0.07421385496854782
+45,,0.22760289907455444,19503,
+46,9.999999747378752e-05,,19927,0.07232991605997086
+46,,0.2254146933555603,19927,
+47,9.999999747378752e-05,,20351,0.07266100496053696
+47,,0.22298133373260498,20351,
+48,9.999999747378752e-05,,20775,0.07445989549160004
+48,,0.22175002098083496,20775,
+49,9.999999747378752e-05,,21199,0.07215843349695206
+49,,0.21755626797676086,21199,
+50,9.999999747378752e-05,,21623,0.07133714854717255
+50,,0.21510690450668335,21623,
+51,9.999999747378752e-05,,22047,0.0713556781411171
+51,,0.21215327084064484,22047,
+52,9.999999747378752e-05,,22471,0.07214436680078506
+52,,0.20858827233314514,22471,
+53,9.999999747378752e-05,,22895,0.07109259814023972
+53,,0.2087220847606659,22895,
+54,9.999999747378752e-05,,23319,0.07146094739437103
+54,,0.20866826176643372,23319,
+55,9.999999747378752e-05,,23743,0.07050544768571854
+55,,0.2037658840417862,23743,
+56,9.999999747378752e-05,,24167,0.06917674839496613
+56,,0.20306703448295593,24167,
+57,9.999999747378752e-05,,24591,0.07003764808177948
+57,,0.1986663043498993,24591,
+58,9.999999747378752e-05,,25015,0.07062102109193802
+58,,0.19890999794006348,25015,
+59,9.999999747378752e-05,,25439,0.07197015732526779
+59,,0.19659635424613953,25439,
+60,9.999999747378752e-05,,25863,0.07174472510814667
+60,,0.19441528618335724,25863,
+61,9.999999747378752e-05,,26287,0.06968678534030914
+61,,0.1919819861650467,26287,
+62,9.999999747378752e-05,,26711,0.07158518582582474
+62,,0.1918257474899292,26711,
+63,9.999999747378752e-05,,27135,0.07025542110204697
+63,,0.18889901041984558,27135,
+64,9.999999747378752e-05,,27559,0.07171856611967087
+64,,0.1903674602508545,27559,
+65,9.999999747378752e-05,,27983,0.0730924904346466
+65,,0.18704192340373993,27983,
+66,9.999999747378752e-05,,28407,0.07027459144592285
+66,,0.18396589159965515,28407,
+67,9.999999747378752e-05,,28831,0.07252991199493408
+67,,0.18247202038764954,28831,
+68,9.999999747378752e-06,,29255,0.07075433433055878
+68,,0.18238519132137299,29255,
+69,9.999999747378752e-06,,29679,0.07024384289979935
+69,,0.18167123198509216,29679,
+70,9.999999747378752e-06,,30103,0.07038987427949905
+70,,0.18080022931098938,30103,
+71,9.999999747378752e-06,,30527,0.07059729099273682
+71,,0.18018695712089539,30527,
+72,9.999999747378752e-06,,30951,0.07024990022182465
+72,,0.17985540628433228,30951,
+73,9.999999747378752e-06,,31375,0.07034288346767426
+73,,0.18019035458564758,31375,
+74,9.999999747378752e-06,,31799,0.07050464302301407
+74,,0.18130117654800415,31799,
+75,9.999999747378752e-06,,32223,0.07073500752449036
+75,,0.18008898198604584,32223,
+76,9.999999747378752e-06,,32647,0.07040064036846161
+76,,0.1794595569372177,32647,

logs/lightning_logs/version_0/events.out.tfevents.1743097022.cn021.1601982.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d84848c58ca2aefccca85ba1a6fde513b752228128875c1b4e296f126e8947a
+size 15326

logs/lightning_logs/version_0/events.out.tfevents.1743097061.cn004.4053787.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc64be71b663e97bea7fa2a3ea1d00587000c44970a903f58789ca3dbe54190
+size 18851

logs/lightning_logs/version_0/hparams.yaml

@@ -0,0 +1,13 @@
+dropout: 0.2
+ensemble_size: 10
+extra_featurizers: null
+learning_rate: 0.0001
+n_hidden: 5
+n_input: 2248
+n_out: 1
+n_units: 16
+optimizer: !!python/name:torch.optim.adam.Adam ''
+reduce_lr_on_plateau: true
+reduce_lr_patience: 10
+use_2d: true
+use_fp: true

metrics.csv

@@ -0,0 +1,4 @@
+split,split_filename,config_i,model_class,n_parameters,filename,features,labels,cache,extra_featurizers,use_2d,use_fp,dropout,ensemble_size,learning_rate,n_hidden,n_units,val_filename,epochs,batch_size,RMSE,Pearson r,Spearman rho
+train,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-train.csv.gz,31,FPMLPModelBox,370890,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-train.csv.gz,['smiles'],['pmic'],/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/models/spark/Francisella-tularensis/31/cache,,True,True,0.2,10,0.0001,5,16,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-validation.csv.gz,2000,16,0.1128498837351799,0.5315396541042405,0.6696014953216823
+validation,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-validation.csv.gz,31,FPMLPModelBox,370890,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-train.csv.gz,['smiles'],['pmic'],/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/models/spark/Francisella-tularensis/31/cache,,True,True,0.2,10,0.0001,5,16,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-validation.csv.gz,2000,16,0.12225893139839172,0.2988704143091524,0.5774266044687701
+test,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-test.csv.gz,31,FPMLPModelBox,370890,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-train.csv.gz,['smiles'],['pmic'],/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/models/spark/Francisella-tularensis/31/cache,,True,True,0.2,10,0.0001,5,16,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-validation.csv.gz,2000,16,0.10296344012022018,0.3527353695023497,0.618750940647444

modelbox-config.json

@@ -0,0 +1,11 @@
+{
+    "dropout": 0.2,
+    "ensemble_size": 10,
+    "extra_featurizers": null,
+    "learning_rate": 0.0001,
+    "model_class": "FPMLPModelBox",
+    "n_hidden": 5,
+    "n_units": 16,
+    "use_2d": true,
+    "use_fp": true
+}

params.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f2ed8906bc0009c6266a5df23d985f883001007c931bd1282a6a1307846af1a
+size 1549446

predictions_test.csv.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79d4846ed3e3721e1be8073c169740f7ba2ca18dd4a300aef7abb048e8a8ad6
+size 1577745

predictions_train.csv.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ef7dd44f4699d8dcab5542da85685f080e8df246bff4a33f5895e3c4537eb9
+size 6527542

predictions_validation.csv.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a331e2554bdcd466931450af466115f313e63ce472fa0e3ff821c0266fac755
+size 1514064

repo-name.txt

@@ -0,0 +1 @@
+scbirlab/spark-dv-2503-ftul

training-args.json

@@ -0,0 +1,5 @@
+{
+    "batch_size": 16,
+    "epochs": 2000,
+    "val_filename": "/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-validation.csv.gz"
+}

training-data.hf/cache-44d673fcffb8a7e3.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ccaae78ca2a3d642b795c6e5a658f3832d10f97f69f0fb3c14a5a7756fe8f5
+size 122659696

training-data.hf/cache-a76fe32afdf81d9d.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f156c8dd5575d670ffd5726bd3c87974337d5febc3a3596ea91d04a6e2b7e515
+size 122659696

training-data.hf/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4028244896cd86ac3cb9686229d7c8d3ac4f0517062a65a0f5833aa8b9853fb0
+size 122152664

training-data.hf/dataset_info.json

@@ -0,0 +1,52 @@
+{
+  "builder_name": "csv",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "csv",
+  "dataset_size": 2688094,
+  "description": "",
+  "download_checksums": {
+    "/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Francisella-tularensis/scaffold-split-train.csv.gz": {
+      "num_bytes": 536218,
+      "checksum": null
+    }
+  },
+  "download_size": 536218,
+  "features": {
+    "smiles": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "inputs": {
+      "feature": {
+        "dtype": "float64",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "labels": {
+      "feature": {
+        "dtype": "float64",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 3224312,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 2688094,
+      "num_examples": 6770,
+      "dataset_name": "csv"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

training-data.hf/state.json

@@ -0,0 +1,15 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "c9efbdfca8a5884e",
+  "_format_columns": null,
+  "_format_kwargs": {
+    "dtype": "float"
+  },
+  "_format_type": "numpy",
+  "_output_all_columns": false,
+  "_split": "train"
+}

training-log.csv

@@ -0,0 +1,78 @@
+epoch,step,learning_rate,loss,val_loss
+0,423,9.999999747378752e-05,9.994428634643556,1.035925030708313
+1,847,9.999999747378752e-05,3.126251697540283,0.6954950094223022
+2,1271,9.999999747378752e-05,2.558513641357422,0.6660816073417664
+3,1695,9.999999747378752e-05,2.1037137508392334,0.5705931186676025
+4,2119,9.999999747378752e-05,1.747497320175171,0.4934812784194946
+5,2543,9.999999747378752e-05,1.4690725803375244,0.3814232051372528
+6,2967,9.999999747378752e-05,1.2258453369140625,0.3409904539585113
+7,3391,9.999999747378752e-05,1.0339215993881226,0.2911608219146728
+8,3815,9.999999747378752e-05,0.9013144969940186,0.2379973977804184
+9,4239,9.999999747378752e-05,0.7816758155822754,0.1998423486948013
+10,4663,9.999999747378752e-05,0.6932660937309265,0.1637083888053894
+11,5087,9.999999747378752e-05,0.6253244876861572,0.1320888251066208
+12,5511,9.999999747378752e-05,0.5718656778335571,0.1164594069123268
+13,5935,9.999999747378752e-05,0.5331162214279175,0.1074078530073165
+14,6359,9.999999747378752e-05,0.5030606389045715,0.0962876975536346
+15,6783,9.999999747378752e-05,0.4715811908245086,0.0901862680912017
+16,7207,9.999999747378752e-05,0.4476066827774048,0.0887942612171173
+17,7631,9.999999747378752e-05,0.4256654381752014,0.0879310742020607
+18,8055,9.999999747378752e-05,0.4078732132911682,0.0886758863925933
+19,8479,9.999999747378752e-05,0.3951185345649719,0.0868586599826812
+20,8903,9.999999747378752e-05,0.3779689073562622,0.0822278186678886
+21,9327,9.999999747378752e-05,0.3682374358177185,0.0816794261336326
+22,9751,9.999999747378752e-05,0.3554483950138092,0.0808927789330482
+23,10175,9.999999747378752e-05,0.3422313630580902,0.0807109102606773
+24,10599,9.999999747378752e-05,0.3378938138484955,0.0794907510280609
+25,11023,9.999999747378752e-05,0.322312980890274,0.0814737975597381
+26,11447,9.999999747378752e-05,0.3146795630455017,0.079401671886444
+27,11871,9.999999747378752e-05,0.3067043125629425,0.0767058879137039
+28,12295,9.999999747378752e-05,0.302741527557373,0.0762641727924346
+29,12719,9.999999747378752e-05,0.2946133017539978,0.0779544860124588
+30,13143,9.999999747378752e-05,0.2926816344261169,0.0771995186805725
+31,13567,9.999999747378752e-05,0.2827025651931762,0.0785115286707878
+32,13991,9.999999747378752e-05,0.2779752314090729,0.0780931487679481
+33,14415,9.999999747378752e-05,0.2712018489837646,0.0780954286456108
+34,14839,9.999999747378752e-05,0.2669171392917633,0.0752025321125984
+35,15263,9.999999747378752e-05,0.2609223127365112,0.0759880617260932
+36,15687,9.999999747378752e-05,0.2556494176387787,0.0762818232178688
+37,16111,9.999999747378752e-05,0.252155065536499,0.0742958113551139
+38,16535,9.999999747378752e-05,0.2488869130611419,0.0737504661083221
+39,16959,9.999999747378752e-05,0.244359016418457,0.0745063126087188
+40,17383,9.999999747378752e-05,0.2419043779373169,0.0731251984834671
+41,17807,9.999999747378752e-05,0.2394701093435287,0.0737960711121559
+42,18231,9.999999747378752e-05,0.2374731451272964,0.0751994252204895
+43,18655,9.999999747378752e-05,0.2326866537332534,0.0737557336688041
+44,19079,9.999999747378752e-05,0.230628415942192,0.0737237855792045
+45,19503,9.999999747378752e-05,0.2276028990745544,0.0742138549685478
+46,19927,9.999999747378752e-05,0.2254146933555603,0.0723299160599708
+47,20351,9.999999747378752e-05,0.2229813337326049,0.0726610049605369
+48,20775,9.999999747378752e-05,0.2217500209808349,0.0744598954916
+49,21199,9.999999747378752e-05,0.2175562679767608,0.072158433496952
+50,21623,9.999999747378752e-05,0.2151069045066833,0.0713371485471725
+51,22047,9.999999747378752e-05,0.2121532708406448,0.0713556781411171
+52,22471,9.999999747378752e-05,0.2085882723331451,0.072144366800785
+53,22895,9.999999747378752e-05,0.2087220847606659,0.0710925981402397
+54,23319,9.999999747378752e-05,0.2086682617664337,0.071460947394371
+55,23743,9.999999747378752e-05,0.2037658840417862,0.0705054476857185
+56,24167,9.999999747378752e-05,0.2030670344829559,0.0691767483949661
+57,24591,9.999999747378752e-05,0.1986663043498993,0.0700376480817794
+58,25015,9.999999747378752e-05,0.1989099979400634,0.070621021091938
+59,25439,9.999999747378752e-05,0.1965963542461395,0.0719701573252677
+60,25863,9.999999747378752e-05,0.1944152861833572,0.0717447251081466
+61,26287,9.999999747378752e-05,0.1919819861650467,0.0696867853403091
+62,26711,9.999999747378752e-05,0.1918257474899292,0.0715851858258247
+63,27135,9.999999747378752e-05,0.1888990104198455,0.0702554211020469
+64,27559,9.999999747378752e-05,0.1903674602508545,0.0717185661196708
+65,27983,9.999999747378752e-05,0.1870419234037399,0.0730924904346466
+66,28407,9.999999747378752e-05,0.1839658915996551,0.0702745914459228
+67,28831,9.999999747378752e-05,0.1824720203876495,0.072529911994934
+68,29255,9.999999747378752e-06,0.1823851913213729,0.0707543343305587
+69,29679,9.999999747378752e-06,0.1816712319850921,0.0702438428997993
+70,30103,9.999999747378752e-06,0.1808002293109893,0.070389874279499
+71,30527,9.999999747378752e-06,0.1801869571208953,0.0705972909927368
+72,30951,9.999999747378752e-06,0.1798554062843322,0.0702499002218246
+73,31375,9.999999747378752e-06,0.1801903545856475,0.0703428834676742
+74,31799,9.999999747378752e-06,0.1813011765480041,0.070504643023014
+75,32223,9.999999747378752e-06,0.1800889819860458,0.0707350075244903
+76,32647,9.999999747378752e-06,0.1794595569372177,0.0704006403684616